Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Joint Computation Offloading and Target Tracking in Integrated Sensing and Communication Enabled UAV Networks

Trinh Van Chien, Mai Dinh Cong, Nguyen Cong Luong, Tri Nhu Do, Dong In Kim, Symeon Chatzinotas

TL;DR

This work tackles the problem of jointly optimizing computation offloading and ground-target velocity tracking in an ISAC-enabled UAV network. It formulates a non-convex objective that minimizes a weighted sum of computation latency and the CRB of velocity estimation by jointly selecting the UAV location and the offloading fraction $\beta$, under a budget constraint. A genetic algorithm is proposed to solve the problem, with a solution representation for $\beta$, $x$, and $y$, and standard GA operators (one-point crossover, polynomial mutation, and tournament survival). Simulations show that the proposed GA outperforms a PSO baseline, revealing the trade-offs between offloading size, UAV compute capacity, and sensing accuracy, and validating the approach for ISAC-enabled UAV networks. The results demonstrate meaningful gains in both latency reduction and velocity-estimation precision, supporting practical deployment and motivating extensions to multi-UAV and clutter-rich environments.

Abstract

In this paper, we investigate a joint computation offloading and target tracking in Integrated Sensing and Communication (ISAC)-enabled unmanned aerial vehicle (UAV) network. Therein, the UAV has a computing task that is partially offloaded to the ground UE for execution. Meanwhile, the UAV uses the offloading bit sequence to estimate the velocity of a ground target based on an autocorrelation function. The performance of the velocity estimation that is represented by Cramer-Rao lower bound (CRB) depends on the length of the offloading bit sequence and the UAV's location. Thus, we jointly optimize the task size for offloading and the UAV's location to minimize the overall computation latency and the CRB of the mean square error for velocity estimation subject to the UAV's budget. The problem is non-convex, and we propose a genetic algorithm to solve it. Simulation results are provided to demonstrate the effectiveness of the proposed algorithm.

Joint Computation Offloading and Target Tracking in Integrated Sensing and Communication Enabled UAV Networks

TL;DR

This work tackles the problem of jointly optimizing computation offloading and ground-target velocity tracking in an ISAC-enabled UAV network. It formulates a non-convex objective that minimizes a weighted sum of computation latency and the CRB of velocity estimation by jointly selecting the UAV location and the offloading fraction , under a budget constraint. A genetic algorithm is proposed to solve the problem, with a solution representation for , , and , and standard GA operators (one-point crossover, polynomial mutation, and tournament survival). Simulations show that the proposed GA outperforms a PSO baseline, revealing the trade-offs between offloading size, UAV compute capacity, and sensing accuracy, and validating the approach for ISAC-enabled UAV networks. The results demonstrate meaningful gains in both latency reduction and velocity-estimation precision, supporting practical deployment and motivating extensions to multi-UAV and clutter-rich environments.

Abstract

In this paper, we investigate a joint computation offloading and target tracking in Integrated Sensing and Communication (ISAC)-enabled unmanned aerial vehicle (UAV) network. Therein, the UAV has a computing task that is partially offloaded to the ground UE for execution. Meanwhile, the UAV uses the offloading bit sequence to estimate the velocity of a ground target based on an autocorrelation function. The performance of the velocity estimation that is represented by Cramer-Rao lower bound (CRB) depends on the length of the offloading bit sequence and the UAV's location. Thus, we jointly optimize the task size for offloading and the UAV's location to minimize the overall computation latency and the CRB of the mean square error for velocity estimation subject to the UAV's budget. The problem is non-convex, and we propose a genetic algorithm to solve it. Simulation results are provided to demonstrate the effectiveness of the proposed algorithm.
Paper Structure (18 sections, 20 equations, 6 figures, 1 table, 1 algorithm)

This paper contains 18 sections, 20 equations, 6 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model
  3. Channel Model
  4. Offloading Time
  5. Offloading Cost
  6. Communication cost
  7. Computation Cost
  8. Target Tracking
  9. Problem Formulation and Genetic Algorithm
  10. Problem Formulation
  11. Genetic Algorithm
  12. Solution Representation
  13. Crossover Operation
  14. Mutation Operation
  15. Survival Selection
  16. ...and 3 more sections

Figures (6)

  • Figure 1:
  • Figure 2:
  • Figure 4:
  • Figure 5:
  • Figure 7:
  • ...and 1 more figures